© 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. 48662
    Prev
    Next
    INDEX
    Explanations

    r

    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
     mouvement
    -0.08
     Grant
    -0.08
    rui
    -0.08
     posição
    -0.08
    liche
    -0.08
     Burma
    -0.07
    শ্য
    -0.07
     deuren
    -0.07
    ộng
    -0.07
     Extraction
    -0.07
    POSITIVE LOGITS
    ummet
    0.10
    idders
    0.09
    iket
    0.09
    iked
    0.09
    ikes
    0.09
    иком
    0.08
    abar
    0.08
    igtig
    0.08
    igtigt
    0.08
    ull
    0.08
    Activations Density 0.000%

    No Known Activations