© 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. 48067
    Prev
    Next
    INDEX
    Explanations

    kne

    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
     הרש
    -0.08
    িউ
    -0.08
    -Key
    -0.08
    -V
    -0.08
    Ө
    -0.08
     molta
    -0.07
     Ө
    -0.07
    ੈਂ
    -0.07
    reuung
    -0.07
    -unit
    -0.07
    POSITIVE LOGITS
    ading
    0.13
    aded
    0.12
    eling
    0.12
    ec
    0.11
    ecimento
    0.10
    epad
    0.10
    ad
    0.09
     Pilates
    0.09
    ads
    0.09
    elings
    0.09
    Activations Density 0.001%

    No Known Activations