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. 43697
    Prev
    Next
    INDEX
    Explanations

    must

    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
     "'",
    -0.08
     enk
    -0.08
    alex
    -0.08
    ?!↵
    -0.08
    're
    -0.07
     rq
    -0.07
    ಾಜಿಕ
    -0.07
     Mittel
    -0.07
     prophyl
    -0.07
     rév
    -0.07
    POSITIVE LOGITS
     Zar
    0.08
     ചെ
    0.08
    -have
    0.08
     Buddy
    0.08
    _cli
    0.07
     poved
    0.07
     underrated
    0.07
    ICY
    0.07
    kinson
    0.07
    -highlight
    0.07
    Activations Density 0.014%

    No Known Activations