© 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. 3-RESID-POST-AA
    11. 1400
    Prev
    Next
    INDEX
    Explanations

    Spanish/Russian languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不仅
    -0.09
     willingly
    -0.08
     जाना
    -0.08
     vip
    -0.08
     voila
    -0.08
    TURN
    -0.08
     предлагает
    -0.08
     plazas
    -0.08
    offers
    -0.08
    Vip
    -0.08
    POSITIVE LOGITS
     constraint
    0.08
    纸
    0.08
     Island
    0.08
     Paper
    0.08
    手续费
    0.07
     beachten
    0.07
    يسة
    0.07
     صرف
    0.07
     Fra
    0.07
    fluence
    0.07
    Activations Density 0.279%

    No Known Activations