© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    ethers
    -0.09
    ether
    -0.08
    avenir
    -0.07
    ETHER
    -0.07
     philos
    -0.07
     Matthew
    -0.07
     Cycling
    -0.07
     breath
    -0.07
     Harold
    -0.07
     fios
    -0.07
    POSITIVE LOGITS
    .subtract
    0.08
    Ls
    0.08
    zás
    0.08
     SELECT
    0.07
    	SELECT
    0.07
     stod
    0.07
    .offset
    0.07
     нат
    0.07
    とな
    0.07
    室
    0.07
    Activations Density 0.056%

    No Known Activations