© 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. 48587
    Prev
    Next
    INDEX
    Explanations

    say "YOUR"

    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
     Taama
    -0.11
     ҵ
    -0.10
     ҟ
    -0.10
     Katonda
    -0.09
     Aamma
    -0.09
     He
    -0.09
     Mukama
    -0.09
     Гагра
    -0.09
    funzi
    -0.09
     In
    -0.09
    POSITIVE LOGITS
     clamp
    0.12
     tr
    0.10
     trap
    0.10
    	gr
    0.10
    (cond
    0.10
     flare
    0.10
     pl
    0.10
    	fr
    0.10
     cond
    0.10
     reg
    0.10
    Activations Density 0.024%

    No Known Activations