© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99225
    Prev
    Next
    INDEX
    Explanations

    to

    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
    _m
    -0.07
    দিকে
    -0.07
    meti
    -0.07
    174
    -0.07
    拒
    -0.07
     salesman
    -0.07
    -0.07
     izle
    -0.07
    icients
    -0.07
    征
    -0.07
    POSITIVE LOGITS
     corrente
    0.09
     الحالي
    0.09
    0.09
    -date
    0.09
    -current
    0.09
     최신
    0.08
     акту
    0.08
     vandaag
    0.08
     أحدث
    0.08
     lacked
    0.08
    Activations Density 0.008%

    No Known Activations