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. 45046
    Prev
    Next
    INDEX
    Explanations

    …

    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
     dioxide
    -0.09
    ಗೆ
    -0.08
    Soul
    -0.07
    pais
    -0.07
    acun
    -0.07
    영상
    -0.07
     પરિવ
    -0.07
     Novel
    -0.07
     gustos
    -0.07
     Symposium
    -0.07
    POSITIVE LOGITS
    ̣
    0.09
     Pach
    0.08
    kom
    0.08
     menstru
    0.07
    cad
    0.07
     meth
    0.07
    �
    0.07
    339
    0.07
     él
    0.07
     Eve
    0.07
    Activations Density 0.025%

    No Known Activations