© 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. 11-RESID-POST-AA
    11. 95257
    Prev
    Next
    INDEX
    Explanations

    work collaborations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inhal
    -0.09
     funnel
    -0.08
     funnels
    -0.08
     swallowed
    -0.08
     grids
    -0.08
     absorption
    -0.08
    %A
    -0.08
     impost
    -0.07
     cigarettes
    -0.07
     buckets
    -0.07
    POSITIVE LOGITS
     συνεργ
    0.12
     yhteisty
    0.12
     сотруднич
    0.12
    合作
    0.12
     rapport
    0.11
    spartner
    0.11
     সহযোগ
    0.11
     साझ
    0.11
     همکاری
    0.10
     আন্ত
    0.10
    Activations Density 0.093%

    No Known Activations