© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47798
    Prev
    Next
    INDEX
    Explanations

    period

    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
    then
    -0.09
    actually
    -0.08
    near
    -0.08
    onet
    -0.08
    again
    -0.08
    _then
    -0.08
    after
    -0.08
    _after
    -0.08
    maybe
    -0.08
    of
    -0.08
    POSITIVE LOGITS
    <|return|>
    0.30
    <|call|>
    0.16
    <|message|>
    0.16
    0.16
    <|constrain|>
    0.15
    0.15
    <|end|>
    0.15
    ↵↵↵↵↵↵↵↵↵↵
    0.15
    <|endoftext|>
    0.14
    <|reserved_200016|>
    0.14
    Activations Density 0.058%

    No Known Activations