© 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. 96727
    Prev
    Next
    INDEX
    Explanations

    الك

    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
    cu
    -0.09
     coarse
    -0.08
     cu
    -0.08
     scint
    -0.08
    cup
    -0.07
     Cu
    -0.07
     COB
    -0.07
    co
    -0.07
    xp
    -0.07
     cren
    -0.07
    POSITIVE LOGITS
     femenino
    0.08
    امن
    0.08
    ಜಿ
    0.08
     vigtigt
    0.08
    ಮಿ
    0.08
    ाला
    0.08
    نسي
    0.08
     ktorý
    0.08
     abon
    0.08
    恐縮
    0.07
    Activations Density 0.000%

    No Known Activations