© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5813
    Prev
    Next
    INDEX
    Explanations

    say white

    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
    _ylabel
    -0.11
    BLACK
    -0.10
     Blackboard
    -0.10
    _BLACK
    -0.10
    Blacklist
    -0.10
     Blacks
    -0.10
     Blackberry
    -0.10
     Secondly
    -0.10
     ブラック
    -0.10
    ブラック
    -0.10
    POSITIVE LOGITS
     white
    0.13
    :white
    0.12
     forth
    0.11
     putih
    0.11
    white
    0.11
     weißen
    0.10
     бел
    0.10
    .white
    0.10
    White
    0.10
    白
    0.10
    Activations Density 0.060%

    No Known Activations