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. 15-RESID-POST-AA
    6. 19619
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {EIF
    -0.09
    ércio
    -0.08
     എന്നാൽ
    -0.08
     означает
    -0.08
     하지만
    -0.08
     części
    -0.08
    �
    -0.08
    vum
    -0.07
    ','=','
    -0.07
     значит
    -0.07
    POSITIVE LOGITS
    ,例如
    0.11
    .↵↵
    0.10
     เช่น
    0.10
    .↵↵↵
    0.10
    ,比如
    0.09
    :↵↵↵
    0.09
    。例如
    0.09
     such
    0.09
    .↵↵↵↵
    0.09
    :↵↵
    0.09
    Activations Density 0.015%

    No Known Activations