© 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. 23-RESID-POST-AA
    11. 51165
    Prev
    Next
    INDEX
    Explanations

    Col

    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
    難
    -0.08
     bili
    -0.08
     Kosov
    -0.07
     referências
    -0.07
     compare
    -0.07
     verwij
    -0.07
     refer
    -0.07
     cylindrical
    -0.07
     H
    -0.07
     öðrum
    -0.07
    POSITIVE LOGITS
    oca
    0.12
    oque
    0.11
    gar
    0.10
    ocado
    0.09
    aps
    0.09
    ocar
    0.09
    599
    0.09
    oco
    0.09
    óc
    0.08
    GAR
    0.08
    Activations Density 0.000%

    No Known Activations