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. 109270
    Prev
    Next
    INDEX
    Explanations

    hide

    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
    'us
    -0.08
    _SUPPORT
    -0.08
     المناسبة
    -0.08
    istance
    -0.08
     Marshall
    -0.08
    נועה
    -0.08
    Oauth
    -0.07
    ...",↵
    -0.07
     organismes
    -0.07
     mouvement
    -0.07
    POSITIVE LOGITS
     concealed
    0.09
    .hidden
    0.09
     hidden
    0.09
     скры
    0.09
    hidden
    0.08
     valuables
    0.08
     Hidden
    0.08
     taxable
    0.08
     verborgen
    0.08
    (hidden
    0.08
    Activations Density 0.002%

    No Known Activations