© 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. 97813
    Prev
    Next
    INDEX
    Explanations

    autofocus

    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
     downturn
    -0.09
     филь
    -0.09
     chimney
    -0.08
     slump
    -0.08
    adows
    -0.08
     stipend
    -0.08
    itlements
    -0.08
     chuva
    -0.08
    ümer
    -0.07
     (-
    -0.07
    POSITIVE LOGITS
     AF
    0.13
    AF
    0.11
     focusing
    0.10
     autofocus
    0.09
    (AF
    0.09
    -ser
    0.09
     Servo
    0.09
    .AF
    0.09
    Focus
    0.09
    锁
    0.09
    Activations Density 0.002%

    No Known Activations