Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58954
    Prev
    Next
    INDEX
    Explanations

    Report sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pion
    -0.08
    巨大
    -0.08
    pine
    -0.07
    ms
    -0.07
    Trips
    -0.07
    survey
    -0.07
     cinn
    -0.07
    443
    -0.07
    tolist
    -0.07
    aas
    -0.07
    POSITIVE LOGITS
     ethical
    0.10
     Ethical
    0.10
     ethics
    0.09
     Ethics
    0.09
     confidentiality
    0.08
     privacy
    0.08
     file
    0.08
    autions
    0.08
    াশ
    0.08
     shame
    0.08
    Activations Density 0.011%

    No Known Activations