© 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. 23-RESID-POST-AA
    11. 49967
    Prev
    Next
    INDEX
    Explanations

    Numeric calculations and roots

    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
    ­den
    -0.08
     gedacht
    -0.08
    ーム
    -0.08
     mór
    -0.08
    ’he
    -0.08
    .builders
    -0.08
     He
    -0.08
     dacht
    -0.07
     pensées
    -0.07
     pienso
    -0.07
    POSITIVE LOGITS
    և
    0.09
     cowork
    0.08
    _at
    0.07
    _string
    0.07
    _context
    0.07
    _tracker
    0.07
     ROOT
    0.07
    ve
    0.07
    rae
    0.07
    _place
    0.07
    Activations Density 0.003%

    No Known Activations