© 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. 99302
    Prev
    Next
    INDEX
    Explanations

    user

    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
    TOT
    -0.08
    ราค
    -0.08
    .Root
    -0.08
    ాలలో
    -0.07
    ราคา
    -0.07
    Instagram
    -0.07
    instagram
    -0.07
     süd
    -0.07
    legenheit
    -0.07
     بارے
    -0.07
    POSITIVE LOGITS
     unaware
    0.09
     obliv
    0.09
     executable
    0.08
    调用
    0.08
    -facing
    0.08
     tərəfindən
    0.08
     tomonidan
    0.08
     powerless
    0.08
    	void
    0.08
    -issued
    0.08
    Activations Density 0.016%

    No Known Activations