© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18739
    Prev
    Next
    INDEX
    Explanations

    Image generation/fantasy prompts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     effective
    -0.08
    	if
    -0.08
    amalla
    -0.08
     identification
    -0.07
     if
    -0.07
    Effective
    -0.07
     Effective
    -0.07
    Validity
    -0.07
     validity
    -0.07
     wanneer
    -0.07
    POSITIVE LOGITS
     futuristic
    0.14
     Fantasy
    0.12
     medieval
    0.12
     మొద
    0.12
     fantasy
    0.12
     různ
    0.11
     разных
    0.11
    Fantasy
    0.11
    幻想
    0.11
     Medieval
    0.11
    Activations Density 0.013%

    No Known Activations