© 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. 54809
    Prev
    Next
    INDEX
    Explanations

    the

    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
     realized
    -0.07
    ın
    -0.07
    φέρ
    -0.07
     penetr
    -0.07
    ład
    -0.07
     thorough
    -0.07
    stuff
    -0.07
     चालक
    -0.07
    lest
    -0.07
    Append
    -0.07
    POSITIVE LOGITS
    袖
    0.08
    -the
    0.08
     cuff
    0.08
     পথে
    0.08
     koup
    0.08
     방식
    0.08
    вычай
    0.08
     покупке
    0.08
     pine
    0.07
     Theo
    0.07
    Activations Density 0.004%

    No Known Activations