Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49843
    Prev
    Next
    INDEX
    Explanations

    cos

    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
     والس
    -0.08
    ியை
    -0.08
     Pedi
    -0.08
     Registration
    -0.08
    Invert
    -0.08
     gehör
    -0.08
    TOT
    -0.08
     Europé
    -0.07
     europäischen
    -0.07
     Christen
    -0.07
    POSITIVE LOGITS
     hen
    0.07
     async
    0.07
     billet
    0.07
    0.07
    Fir
    0.07
    ဂ
    0.07
     gun
    0.07
     ระ
    0.07
    Impact
    0.07
     activist
    0.07
    Activations Density 0.000%

    No Known Activations