© 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. 102698
    Prev
    Next
    INDEX
    Explanations

    instructions format

    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
    1
    -0.12
    "
    -0.10
    ..."
    -0.10
    "?
    -0.09
    :
    -0.09
    -II
    -0.09
    ...'
    -0.09
    ১
    -0.08
    2
    -0.08
    ing
    -0.08
    POSITIVE LOGITS
    　　↵
    0.11
    ‬↵
    0.11
    <|return|>
    0.10
     ###
    0.10
    　↵
    0.10
    ۔↵
    0.10
     While
    0.10
     หาก
    0.10
    。↵↵↵↵↵
    0.09
    ạt
    0.09
    Activations Density 0.028%

    No Known Activations