Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 52978
    Prev
    Next
    INDEX
    Explanations

    prime

    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
    VENT
    -0.08
    cryption
    -0.08
    .bo
    -0.08
    crypted
    -0.07
     Encryption
    -0.07
    TRAN
    -0.07
     VEN
    -0.07
    Bits
    -0.07
     Natal
    -0.07
    .billing
    -0.07
    POSITIVE LOGITS
     هغه
    0.10
    .Atoi
    0.09
     polícia
    0.08
     cops
    0.08
     robber
    0.08
     ಪೊಲೀಸರು
    0.08
     غوره
    0.08
     invading
    0.08
     apple
    0.08
     lawv
    0.08
    Activations Density 0.002%

    No Known Activations