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. 44050
    Prev
    Next
    INDEX
    Explanations

    ask

    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
    Fee
    -0.08
    עמ
    -0.08
    ofilm
    -0.08
     autod
    -0.08
    Dump
    -0.08
    TLS
    -0.07
    SV
    -0.07
     Fee
    -0.07
    GV
    -0.07
     dump
    -0.07
    POSITIVE LOGITS
     politely
    0.09
     unanswered
    0.09
    iň
    0.08
    /reg
    0.08
     höf
    0.08
    ~":"
    0.07
    หรือ
    0.07
    /question
    0.07
     메시
    0.07
    ాం�
    0.07
    Activations Density 0.012%

    No Known Activations