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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 46989
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ahid
    -0.09
    .per
    -0.08
    _cat
    -0.07
    jal
    -0.07
    YY
    -0.07
    -social
    -0.07
    avicon
    -0.07
    IMP
    -0.07
    DEC
    -0.07
    cat
    -0.07
    POSITIVE LOGITS
    ?
    0.11
     eher
    0.11
     lieber
    0.11
    ?",
    0.10
     vielmehr
    0.10
    ?”
    0.10
    ՞
    0.10
    还是
    0.10
    ?↵↵
    0.10
    ?”
    0.10
    Activations Density 0.047%

    No Known Activations