© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6053
    Prev
    Next
    INDEX
    Explanations

    dialogue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     integrada
    -0.09
     الرقم
    -0.09
     yoğun
    -0.08
     convocatoria
    -0.08
     intimately
    -0.08
    猛烈
    -0.08
     wewe
    -0.08
     integrado
    -0.08
     呼
    -0.08
    ీరో
    -0.08
    POSITIVE LOGITS
     પસ
    0.13
     attravers
    0.12
     crosses
    0.12
    -cross
    0.12
     crossed
    0.11
     pasar
    0.11
     appeared
    0.10
    _cross
    0.10
    cross
    0.10
     passage
    0.10
    Activations Density 0.033%

    No Known Activations