© 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. 26601
    Prev
    Next
    INDEX
    Explanations

    Mathematical expressions

    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
     svensk
    -0.07
     komplet
    -0.07
    tid
    -0.07
    abler
    -0.07
     dialect
    -0.07
     પૂર
    -0.07
    డియ
    -0.07
     rear
    -0.07
     كامل
    -0.07
    imental
    -0.07
    POSITIVE LOGITS
    Yi
    0.09
     asociado
    0.09
     yi
    0.08
     değer
    0.08
     asociados
    0.08
    üh
    0.08
     angenommen
    0.08
     ordinate
    0.08
    Pada
    0.08
     correspondente
    0.08
    Activations Density 0.083%

    No Known Activations