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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97332
    Prev
    Next
    INDEX
    Explanations

    ы

    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
    орами
    -0.10
    rí
    -0.09
     নয়
    -0.08
     নয়
    -0.08
    ريد
    -0.08
     Faktoren
    -0.08
     Einrichtungen
    -0.08
    POCH
    -0.08
     desaf
    -0.08
    rachten
    -0.08
    POSITIVE LOGITS
    ден
    0.10
    .cz
    0.08
    বর্ত
    0.08
    shëm
    0.08
     currently
    0.07
    shme
    0.07
    Currently
    0.07
    din
    0.07
    de
    0.07
    currently
    0.07
    Activations Density 0.000%

    No Known Activations