© 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. 97222
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     khó
    -0.08
     vilken
    -0.07
    -labelledby
    -0.07
    hom
    -0.07
     alignment
    -0.07
     desconoc
    -0.07
     offenders
    -0.07
     hom
    -0.07
    .pre
    -0.07
     зрел
    -0.07
    POSITIVE LOGITS
     pursuits
    0.08
     xiri
    0.08
    SOC
    0.08
    .Logging
    0.08
     COURSE
    0.07
    عى
    0.07
     FACEBOOK
    0.07
     ур
    0.07
    Cours
    0.07
    ్చ
    0.07
    Activations Density 0.000%

    No Known Activations