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. 58886
    Prev
    Next
    INDEX
    Explanations

    Periods

    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
    (t
    -0.07
     रखते
    -0.07
     prób
    -0.07
    -0.07
    -0.07
    _hat
    -0.07
    (head
    -0.06
    -0.06
    _even
    -0.06
    ِين
    -0.06
    POSITIVE LOGITS
    ,param
    0.08
     ويل
    0.07
     ప్రమ
    0.07
    栏目
    0.07
    iriza
    0.07
     rote
    0.07
    广东
    0.07
    282
    0.07
    renal
    0.07
     innumer
    0.07
    Activations Density 0.029%

    No Known Activations