© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48782
    Prev
    Next
    INDEX
    Explanations

    Basketball stats

    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
     trainen
    -0.08
    ynomials
    -0.08
     produktów
    -0.08
    arschijnlijk
    -0.08
     möchten
    -0.08
     betrachten
    -0.08
     curricula
    -0.08
     betalen
    -0.08
    ி�
    -0.08
     wanting
    -0.08
    POSITIVE LOGITS
     steals
    0.19
     assists
    0.17
     assist
    0.14
     steal
    0.14
    助
    0.14
     assisting
    0.14
     stealing
    0.14
     interceptions
    0.14
     assistência
    0.13
     asist
    0.13
    Activations Density 0.032%

    No Known Activations