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. 90062
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
     محافظ
    -0.08
    Inf
    -0.08
     fortunate
    -0.08
    inf
    -0.07
    _found
    -0.07
    _attr
    -0.07
    _inf
    -0.07
     rub
    -0.07
     concentration
    -0.07
    .Where
    -0.07
    POSITIVE LOGITS
     toggle
    0.09
    /reset
    0.08
    .toggle
    0.08
     Pellet
    0.08
     загруз
    0.08
     Toggle
    0.08
    -toggle
    0.08
    (toggle
    0.08
    ельно
    0.08
    لفة
    0.08
    Activations Density 0.012%

    No Known Activations