© 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. 48036
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    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
    FSM
    -0.08
     Clickfunnels
    -0.08
    FN
    -0.08
     klikken
    -0.08
     Fourier
    -0.08
    .flink
    -0.08
     direita
    -0.08
     αποτελεί
    -0.07
     compressors
    -0.07
    Frontend
    -0.07
    POSITIVE LOGITS
     SK
    0.09
    ars
    0.09
    (sk
    0.08
    ark
    0.08
    uds
    0.07
    gs
    0.07
    (SK
    0.07
     yoğun
    0.07
     kg
    0.07
     ku
    0.07
    Activations Density 0.001%

    No Known Activations