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. 24004
    Prev
    Next
    INDEX
    Explanations

    bicycles

    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
     wrapped
    -0.07
     wrapping
    -0.07
    MOD
    -0.07
     Professor
    -0.07
     sentence
    -0.07
     Zan
    -0.07
    Lex
    -0.07
     scen
    -0.07
     Department
    -0.07
     बोल
    -0.07
    POSITIVE LOGITS
     delanter
    0.09
    _bundle
    0.09
     buckle
    0.08
    ిల్
    0.08
    _overlap
    0.08
    เตอรี่
    0.08
     wob
    0.08
     hesitation
    0.08
     الرأس
    0.08
    .bootstrap
    0.08
    Activations Density 0.010%

    No Known Activations