© 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. 48704
    Prev
    Next
    INDEX
    Explanations

    hairstyles

    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
     жилья
    -0.09
    வரி
    -0.09
     Zusch
    -0.08
     LAND
    -0.08
    _logits
    -0.08
     生命周期函数
    -0.08
    .print
    -0.08
     humaines
    -0.08
    ورش
    -0.08
     ανθ
    -0.08
    POSITIVE LOGITS
     bun
    0.14
     buns
    0.14
     pony
    0.13
     messy
    0.12
     neat
    0.12
     braid
    0.12
     tidy
    0.11
     Pony
    0.11
    bun
    0.10
     sleek
    0.10
    Activations Density 0.016%

    No Known Activations