© 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. 47924
    Prev
    Next
    INDEX
    Explanations

    Start of stories

    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
    icode
    -0.08
     cens
    -0.08
     SIG
    -0.08
    Deb
    -0.08
    ustering
    -0.07
    amt
    -0.07
    ürd
    -0.07
     subdiv
    -0.07
    умен
    -0.07
    .El
    -0.07
    POSITIVE LOGITS
     pron
    0.10
     directa
    0.10
     პირ
    0.10
     personable
    0.10
     langsung
    0.10
     experien
    0.10
     مباشرة
    0.09
     лично
    0.09
     pengalaman
    0.09
     الذات
    0.09
    Activations Density 0.117%

    No Known Activations