© 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. 96760
    Prev
    Next
    INDEX
    Explanations

    script dialogue

    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
    ીઆ
    -0.10
    ર્સ
    -0.08
    িআ
    -0.08
    톤
    -0.08
    Vest
    -0.08
    ર્શ
    -0.08
    іта
    -0.08
     abaz
    -0.07
    ишк
    -0.07
     Grant
    -0.07
    POSITIVE LOGITS
    attering
    0.14
    anned
    0.11
    oking
    0.11
    anning
    0.10
    atted
    0.10
    attered
    0.09
    actoring
    0.09
    atting
    0.09
    opping
    0.09
    ottages
    0.09
    Activations Density 0.014%

    No Known Activations