© 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. 19-RESID-POST-AA
    11. 102946
    Prev
    Next
    INDEX
    Explanations

    invalid input

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     at
    -0.08
     a
    -0.07
     represent
    -0.07
    ’article
    -0.07
     final
    -0.07
    final
    -0.07
    gevity
    -0.07
     finalize
    -0.07
     llegando
    -0.07
     máxima
    -0.07
    POSITIVE LOGITS
    .invalid
    0.15
     Incorrect
    0.15
     Retry
    0.15
    _invalid
    0.14
    _retry
    0.14
     retry
    0.14
    Retry
    0.14
     opnieuw
    0.14
     incorrect
    0.14
    incorrect
    0.14
    Activations Density 0.005%

    No Known Activations