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. 111401
    Prev
    Next
    INDEX
    Explanations

    Linux commands

    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
     Series
    -0.10
     શેર
    -0.09
    downs
    -0.08
     પરિણ
    -0.08
     kuti
    -0.08
     Down
    -0.08
     Sar
    -0.08
     أن
    -0.08
     شریک
    -0.07
     सिर्�
    -0.07
    POSITIVE LOGITS
    .tool
    0.08
    发挥
    0.08
     довер
    0.07
    .page
    0.07
    ecu
    0.07
    Им
    0.07
    Reached
    0.07
    canner
    0.07
     trusting
    0.07
    /
    ↵
    ↵
    0.07
    Activations Density 0.001%

    No Known Activations