© 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. 48150
    Prev
    Next
    INDEX
    Explanations

    rhetoric/language

    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
     Uns
    -0.09
     roa
    -0.08
     эш
    -0.08
    orris
    -0.08
     suomal
    -0.08
     Schatten
    -0.08
    эль
    -0.07
     Unter
    -0.07
     күрә
    -0.07
     dessous
    -0.07
    POSITIVE LOGITS
     nectar
    0.08
     तकनी
    0.08
    CTR
    0.08
    CCESS
    0.07
    	cc
    0.07
     geil
    0.07
     proiz
    0.07
     Logos
    0.07
     नेताओं
    0.07
    ensity
    0.07
    Activations Density 0.000%

    No Known Activations