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. 65147
    Prev
    Next
    INDEX
    Explanations

    Maximum value

    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
     dipped
    -0.09
     LC
    -0.08
     mixtures
    -0.08
     dipping
    -0.08
     trip
    -0.08
     Rotate
    -0.08
     tour
    -0.08
     পৃথিব
    -0.08
     未
    -0.07
     소재
    -0.07
    POSITIVE LOGITS
     integer
    0.11
     ceil
    0.10
    ceil
    0.10
    floor
    0.10
    整数
    0.10
     floor
    0.09
    Integer
    0.09
    _integer
    0.09
    .integer
    0.09
    integer
    0.08
    Activations Density 0.022%

    No Known Activations