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. 53194
    Prev
    Next
    INDEX
    Explanations

    ID numbers

    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
    PROPERTY
    -0.08
    (mod
    -0.08
     mód
    -0.08
    ạm
    -0.08
     संश
    -0.07
    (property
    -0.07
     ntụ
    -0.07
    .FILL
    -0.07
     ulik
    -0.07
    ुलाई
    -0.07
    POSITIVE LOGITS
     પર
    0.07
    ರಲ್ಲಿ
    0.07
     Hudson
    0.07
     filesystem
    0.07
    567
    0.07
    ცა
    0.07
     impres
    0.07
     Amph
    0.07
    882
    0.07
    405
    0.07
    Activations Density 0.000%

    No Known Activations