© 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. 48588
    Prev
    Next
    INDEX
    Explanations

    Wy

    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
    πους
    -0.08
     Umm
    -0.08
    quilo
    -0.08
    عون
    -0.08
    ayeen
    -0.07
     bato
    -0.07
    傅
    -0.07
     sekä
    -0.07
    _uv
    -0.07
     신고
    -0.07
    POSITIVE LOGITS
    oming
    0.14
    vern
    0.13
    bodaeth
    0.12
    żs
    0.10
    AND
    0.10
    ETH
    0.10
    eth
    0.10
    and
    0.09
    cliffe
    0.09
    świet
    0.09
    Activations Density 0.004%

    No Known Activations