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. 113839
    Prev
    Next
    INDEX
    Explanations

    policy compliance

    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
    angements
    -0.09
    ‘I
    -0.08
     grotes
    -0.08
     terrifying
    -0.08
    adi
    -0.08
    arehouse
    -0.08
    ’Brien
    -0.08
    urg
    -0.07
    ueling
    -0.07
    riors
    -0.07
    POSITIVE LOGITS
     안내
    0.09
     coverage
    0.08
     solic
    0.08
     Covered
    0.08
     referral
    0.08
     entice
    0.08
     запрещ
    0.08
    -covered
    0.08
     നൽക
    0.08
    Providing
    0.08
    Activations Density 0.072%

    No Known Activations