© 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. 11-RESID-POST-AA
    11. 78490
    Prev
    Next
    INDEX
    Explanations

    again

    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
     Danach
    -0.08
     slam
    -0.08
     Skinny
    -0.08
     EM
    -0.08
     Bull
    -0.08
     Slam
    -0.07
     judgment
    -0.07
     endorsement
    -0.07
     grids
    -0.07
    Gra
    -0.07
    POSITIVE LOGITS
    spot
    0.08
    STATUS
    0.07
     এব
    0.07
    prec
    0.07
    ところ
    0.07
    _content
    0.07
    百
    0.07
     �
    0.07
    )};↵
    0.07
     таки
    0.07
    Activations Density 0.007%

    No Known Activations