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. 61114
    Prev
    Next
    INDEX
    Explanations

    of

    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
    (mat
    -0.08
    ుట
    -0.08
    ITAL
    -0.08
    $↵↵
    -0.08
    isers
    -0.07
    _out
    -0.07
    `;↵↵
    -0.07
    PL
    -0.07
    995
    -0.07
    shot
    -0.07
    POSITIVE LOGITS
     greatness
    0.09
     mascul
    0.09
     بری
    0.09
     بـ
    0.09
     excellence
    0.09
     constitutes
    0.08
     bass
    0.08
     belonging
    0.08
     constituye
    0.08
    cellence
    0.08
    Activations Density 0.042%

    No Known Activations