© 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. 30175
    Prev
    Next
    INDEX
    Explanations

    Q

    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
     bilde
    -0.08
     Nr
    -0.07
    築
    -0.07
     மூ
    -0.07
     """
↵
    -0.06
     PAG
    -0.06
     relations
    -0.06
     Ig
    -0.06
    emann
    -0.06
     Said
    -0.06
    POSITIVE LOGITS
     accomp
    0.08
    eiro
    0.08
    /menu
    0.08
     מוכ
    0.08
     Bleu
    0.08
    ',{
    0.08
    upunct
    0.07
     disciples
    0.07
    grade
    0.07
     glyc
    0.07
    Activations Density 0.001%

    No Known Activations