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. 395
    Prev
    Next
    INDEX
    Explanations

    Certainty

    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
     syntax
    -0.08
     Susp
    -0.07
     Wes
    -0.07
     morphological
    -0.07
    USP
    -0.07
     relative
    -0.07
     ill
    -0.07
    .r
    -0.06
    Susp
    -0.06
     Pir
    -0.06
    POSITIVE LOGITS
    습니까
    0.09
    르고
    0.09
    나요
    0.09
    bije
    0.09
     счит
    0.09
    -нибудь
    0.08
    인가
    0.08
    ોર્ડ
    0.08
    -də
    0.08
     Sung
    0.08
    Activations Density 0.087%

    No Known Activations