© 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. 11-RESID-POST-AA
    11. 91246
    Prev
    Next
    INDEX
    Explanations

    knitting and crocheting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facilities
    -0.09
     mă
    -0.08
     دست
    -0.08
     bestätigen
    -0.08
     طور
    -0.08
    发现
    -0.08
     beschikking
    -0.08
     കണ്ടെത്ത
    -0.08
    执行
    -0.07
    Facilities
    -0.07
    POSITIVE LOGITS
     neckline
    0.10
     taper
    0.09
     tapered
    0.09
     layers
    0.09
     Layers
    0.08
    udad
    0.08
     boyunca
    0.08
     Thick
    0.08
    0.08
     thick
    0.08
    Activations Density 0.015%
    No Known Activations