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

    Neuronpedia

    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. 97567
    Prev
    Next
    INDEX
    Explanations

    m

    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
     variantes
    -0.09
     spune
    -0.08
     ness
    -0.08
    SM
    -0.07
     stopper
    -0.07
     pev
    -0.07
    _PRINTF
    -0.07
    -0.07
     tó
    -0.07
     states
    -0.07
    POSITIVE LOGITS
    acheter
    0.09
    oureuse
    0.09
    elle
    0.08
    acción
    0.08
    avenir
    0.08
    Kala
    0.08
    аки
    0.08
    enue
    0.07
    imbursement
    0.07
    0.07
    Activations Density 0.003%
    No Known Activations