© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69187
    Prev
    Next
    INDEX
    Explanations

    audio

    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
     barred
    -0.08
     submiss
    -0.08
    	panic
    -0.08
     NDA
    -0.07
     protested
    -0.07
     mailbox
    -0.07
     leite
    -0.07
     elliptical
    -0.07
     With
    -0.07
     dominated
    -0.07
    POSITIVE LOGITS
     экскур
    0.09
     Podcasts
    0.09
     tourists
    0.08
     downloadable
    0.08
     Museums
    0.08
     бағдарлам
    0.08
     Museum
    0.08
    useid
    0.08
     podcasts
    0.08
    Museum
    0.08
    Activations Density 0.010%

    No Known Activations