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. 43633
    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
     alternative
    -0.09
     Hindu
    -0.08
    dies
    -0.08
    -exp
    -0.07
    uada
    -0.07
    ternative
    -0.07
     Zeit
    -0.07
     Dum
    -0.07
     função
    -0.07
    ifferent
    -0.07
    POSITIVE LOGITS
    етров
    0.08
     और
    0.08
    0.08
     भय
    0.08
    0.08
     וס
    0.07
     ಹಾಗೂ
    0.07
    arah
    0.07
    、『
    0.07
    、第
    0.07
    Activations Density 0.062%

    No Known Activations