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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1500
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sweep
    -0.08
     Danielle
    -0.08
    heat
    -0.07
     sweep
    -0.07
     crowdfunding
    -0.07
     freelance
    -0.07
     exp
    -0.07
     granular
    -0.07
     Freel
    -0.07
     flagged
    -0.07
    POSITIVE LOGITS
     sayings
    0.09
     philosophical
    0.08
     tav
    0.08
     ö
    0.08
     깨
    0.08
     alaye
    0.08
     scripture
    0.08
     Ejecut
    0.08
    ನು
    0.08
     이
    0.08
    Activations Density 0.002%

    No Known Activations