© 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. 103023
    Prev
    Next
    INDEX
    Explanations

    Diagrams as code

    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
     the
    -0.11
     both
    -0.10
     a
    -0.09
     our
    -0.09
     at
    -0.09
     some
    -0.09
     **
    -0.09
     (**
    -0.08
    —
    -0.08
     more
    -0.08
    POSITIVE LOGITS
    plib
    0.12
    .environment
    0.11
    環
    0.10
    <|message|>
    0.10
    graphics
    0.09
    /mp
    0.09
    /png
    0.09
    -language
    0.09
    /stdc
    0.09
    �का
    0.09
    Activations Density 0.001%

    No Known Activations