© 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. 47309
    Prev
    Next
    INDEX
    Explanations

    1

    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
     buscando
    -0.07
     vara
    -0.07
     bande
    -0.07
    (pow
    -0.07
     portions
    -0.07
     vale
    -0.07
    ιν
    -0.07
     sö
    -0.07
    210
    -0.07
     pse
    -0.07
    POSITIVE LOGITS
     seas
    0.08
    iveren
    0.08
     backlink
    0.08
    HEST
    0.08
    heated
    0.08
    Creo
    0.07
     Raid
    0.07
     reefs
    0.07
     Overseas
    0.07
     erotische
    0.07
    Activations Density 0.008%

    No Known Activations