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. 49305
    Prev
    Next
    INDEX
    Explanations

    disallowed content

    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
     rectangular
    -0.09
     Σ
    -0.08
     केवल
    -0.08
    Operand
    -0.08
     diameter
    -0.08
     man's
    -0.08
    Variable
    -0.08
     elasticity
    -0.07
    <List
    -0.07
    -0.07
    POSITIVE LOGITS
     defamatory
    0.11
     authoritarian
    0.11
     extremist
    0.10
     misconduct
    0.10
    侵犯
    0.10
     hateful
    0.10
     оруж
    0.10
     наркот
    0.10
     profanity
    0.10
     condemn
    0.10
    Activations Density 0.030%

    No Known Activations