© 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. 51164
    Prev
    Next
    INDEX
    Explanations

    say isan words

    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
    erd
    -0.08
    erdere
    -0.08
    ென
    -0.08
    eerd
    -0.08
    erder
    -0.07
    entes
    -0.07
    mands
    -0.07
    licts
    -0.07
     yose
    -0.07
    ിച്ചിരുന്നു
    -0.07
    POSITIVE LOGITS
    ian
    0.10
    juan
    0.10
    хана
    0.10
    isan
    0.09
    angian
    0.09
    ahinta
    0.09
    রণ
    0.09
    ание
    0.09
    angan
    0.09
    aimana
    0.09
    Activations Density 0.003%

    No Known Activations