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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110378
    Prev
    Next
    INDEX
    Explanations

    error handling

    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
     bows
    -0.08
     recipro
    -0.08
    Same
    -0.08
    Experimental
    -0.07
     Reciprocity
    -0.07
    Following
    -0.07
     Gener
    -0.07
    Research
    -0.07
     envers
    -0.07
    Optimize
    -0.07
    POSITIVE LOGITS
    转换
    0.11
     conversion
    0.10
    isdigit
    0.10
    	parse
    0.09
    .parse
    0.09
    _parse
    0.09
     convertible
    0.08
     parsing
    0.08
    oboye
    0.08
     మాట్లాడ
    0.08
    Activations Density 0.014%

    No Known Activations