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. 98314
    Prev
    Next
    INDEX
    Explanations

    p

    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
     prze
    -0.10
    484
    -0.09
     posiada
    -0.09
     Suisse
    -0.08
    ist
    -0.08
     Switzerland
    -0.08
    istas
    -0.08
     sleepers
    -0.08
     dispone
    -0.07
    orset
    -0.07
    POSITIVE LOGITS
    ipa
    0.10
    יכ
    0.08
    erc
    0.08
    ਿਆ
    0.08
    inition
    0.08
    ્યાન
    0.08
    නය
    0.08
    ેડ
    0.08
    ிப்ப
    0.07
    נ
    0.07
    Activations Density 0.000%

    No Known Activations