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. 23665
    Prev
    Next
    INDEX
    Explanations

    (-

    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
     dart
    -0.07
     fishing
    -0.07
     Kate
    -0.07
     Mount
    -0.07
    -0.07
    .');↵↵
    -0.07
     Glob
    -0.07
    иса
    -0.07
     autor
    -0.07
     손
    -0.07
    POSITIVE LOGITS
    Does
    0.08
     wcześniej
    0.08
    去年
    0.08
    cep
    0.08
     quattro
    0.08
     SVN
    0.08
     does
    0.08
    does
    0.08
    prechen
    0.08
    spar
    0.08
    Activations Density 0.010%

    No Known Activations