© 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 EvalsExportsAPI 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. 69758
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     കൈ
    -0.07
     upr
    -0.07
    Red
    -0.07
     수도
    -0.07
    /f
    -0.07
     rebates
    -0.07
    topia
    -0.06
     Ramp
    -0.06
    /home
    -0.06
    Pads
    -0.06
    POSITIVE LOGITS
    whatever
    0.09
    -spe
    0.09
     whichever
    0.09
     determinar
    0.09
     iff
    0.09
     cuales
    0.08
     Whatever
    0.08
    endlela
    0.08
    至少
    0.08
     Mereka
    0.08
    Activations Density 0.154%

    No Known Activations