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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98358
    Prev
    Next
    INDEX
    Explanations

    zost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иками
    -0.08
    ики
    -0.08
    ика
    -0.08
    ике
    -0.08
    ILLISECONDS
    -0.08
    verbs
    -0.07
    uyi
    -0.07
    ически
    -0.07
     Tracy
    -0.07
     Nap
    -0.07
    POSITIVE LOGITS
    ępu
    0.17
    ąpi
    0.14
    arczy
    0.13
    aw
    0.12
    awić
    0.12
    ęp
    0.11
    awy
    0.10
    anie
    0.10
    ają
    0.10
    AW
    0.10
    Activations Density 0.000%

    No Known Activations