© 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. 48234
    Prev
    Next
    INDEX
    Explanations

    Hers

    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
     uj
    -0.08
    uwur
    -0.08
    uencia
    -0.08
    ianza
    -0.07
    ুৱা
    -0.07
     Tao
    -0.07
    uzwa
    -0.07
    уре
    -0.07
     vaihtoe
    -0.07
     investi
    -0.07
    POSITIVE LOGITS
    hey
    0.13
    chel
    0.12
    HEY
    0.11
    chell
    0.11
    chelle
    0.10
    hel
    0.10
    hk
    0.08
    bruck
    0.08
    ENTO
    0.08
    ellä
    0.08
    Activations Density 0.004%

    No Known Activations