© 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. 6012
    Prev
    Next
    INDEX
    Explanations

    discipline

    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
    mik
    -0.08
    ents
    -0.08
    -0.08
    urar
    -0.07
    osite
    -0.07
     ENT
    -0.07
    ash
    -0.07
    ard
    -0.07
     ARE
    -0.07
     mg
    -0.07
    POSITIVE LOGITS
    лины
    0.19
    лина
    0.16
    iplina
    0.16
    лини
    0.14
    ziplin
    0.12
    pline
    0.12
    лин
    0.11
    cipline
    0.11
    цип
    0.11
    liner
    0.11
    Activations Density 0.001%
    No Known Activations