© 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. 23-RESID-POST-AA
    11. 6120
    Prev
    Next
    INDEX
    Explanations

    LaTeX expressions

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (`
    -0.11
     !=
    -0.10
     <=
    -0.10
     (_
    -0.10
     ($_
    -0.10
     Ë
    -0.10
     ($
    -0.09
     P
    -0.09
     (:
    -0.09
     ν
    -0.09
    POSITIVE LOGITS
    \
    0.18
    \[
    0.17
    \(
    0.16
    The
    0.13
    Given
    0.12
    Using
    0.12
    ---↵
    0.11
    Let
    0.11
     
    0.11
    \Models
    0.11
    Activations Density 0.037%

    No Known Activations