© 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. 19140
    Prev
    Next
    INDEX
    Explanations

    施

    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
     ट्रेन
    -0.10
     प्रथम
    -0.09
    dez
    -0.09
     त्यांच्या
    -0.09
     צוות
    -0.09
    เอียด
    -0.08
    体验金
    -0.08
    	UObject
    -0.08
    .king
    -0.08
     nước
    -0.08
    POSITIVE LOGITS
     imposed
    0.10
     burdens
    0.10
    BL
    0.09
    bl
    0.09
    web
    0.09
     blamed
    0.08
     burden
    0.08
    position
    0.08
    mentioned
    0.08
    charg
    0.08
    Activations Density 0.015%

    No Known Activations