Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48125
    Prev
    Next
    INDEX
    Explanations

    produce

    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
     Centr
    -0.08
    promotion
    -0.08
    124
    -0.08
     проходят
    -0.08
     namely
    -0.07
    mob
    -0.07
     занятия
    -0.07
     Massa
    -0.07
     drums
    -0.07
    ्रम
    -0.07
    POSITIVE LOGITS
    @m
    0.09
    ively
    0.08
     intellig
    0.08
     compelling
    0.08
     persuasive
    0.08
     صور
    0.07
     intelligent
    0.07
    formatted
    0.07
    ಬ್ಬ
    0.07
     essentially
    0.07
    Activations Density 0.037%

    No Known Activations