© 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. 5980
    Prev
    Next
    INDEX
    Explanations

    l

    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
    tris
    -0.08
     Eff
    -0.08
     presses
    -0.08
     ثانية
    -0.07
    150
    -0.07
    olated
    -0.07
     tokenizer
    -0.07
     greater
    -0.07
    greater
    -0.07
    Tokenizer
    -0.07
    POSITIVE LOGITS
    ư
    0.09
    ilyn
    0.09
    .relationship
    0.08
    ihanna
    0.08
     Rory
    0.08
    onal
    0.08
    incinnati
    0.08
    	stmt
    0.08
    ihar
    0.08
    琳
    0.08
    Activations Density 0.000%

    No Known Activations