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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65224
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

    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
    segment
    -0.09
    Segment
    -0.08
    exp
    -0.08
    _segment
    -0.07
    maximum
    -0.07
    sector
    -0.07
     segment
    -0.07
     facial
    -0.07
    graph
    -0.07
    ensemble
    -0.07
    POSITIVE LOGITS
     სტუდ
    0.10
    აფერი
    0.10
     գտնվող
    0.10
     տնօրեն
    0.09
    ՞նչ
    0.09
     კით
    0.09
    ՞
    0.09
     уҡы
    0.09
     ვიცი
    0.09
     기준
    0.09
    Activations Density 0.069%

    No Known Activations