© 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. 19-RESID-POST-AA
    11. 102677
    Prev
    Next
    INDEX
    Explanations

    Baking doneness

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anytime
    -0.09
     input
    -0.08
     further
    -0.08
     anything
    -0.07
     adjust
    -0.07
     Sub
    -0.07
     subt
    -0.07
     adjusting
    -0.07
    лек
    -0.07
     vidare
    -0.07
    POSITIVE LOGITS
     moist
    0.09
    חת
    0.09
     两
    0.09
     schöner
    0.09
    attachments
    0.09
     werkdagen
    0.09
    דער
    0.08
    indlela
    0.08
     влаж
    0.08
     crumbs
    0.08
    Activations Density 0.000%

    No Known Activations