© 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. 68160
    Prev
    Next
    INDEX
    Explanations

    response

    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
    wide
    -0.08
    comma
    -0.07
    igma
    -0.07
     \↵
    -0.07
    ouble
    -0.07
    .complete
    -0.07
    -0.07
     Paste
    -0.07
    ;\↵
    -0.07
     smoke
    -0.07
    POSITIVE LOGITS
     ngendlela
    0.08
    angebot
    0.08
     escrito
    0.08
    邀请
    0.08
     escritos
    0.07
     faucibus
    0.07
     vanuit
    0.07
    Invite
    0.07
    글
    0.07
    angebote
    0.07
    Activations Density 0.017%
    No Known Activations