© 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. 97275
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ्रो
    -0.08
    ילי
    -0.08
    זק
    -0.08
    ਜ਼
    -0.08
     Serum
    -0.07
    -Z
    -0.07
    .Z
    -0.07
     zm
    -0.07
     Z
    -0.07
     झ
    -0.07
    POSITIVE LOGITS
     WHETHER
    0.09
    aturi
    0.08
     diab
    0.08
    ighting
    0.07
    akw
    0.07
    iligen
    0.07
    isuus
    0.07
    เดียว
    0.07
     dialogue
    0.07
    યો
    0.07
    Activations Density 0.001%

    No Known Activations