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. 53457
    Prev
    Next
    INDEX
    Explanations

    blood

    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
    ಾಕ
    -0.08
    ,此
    -0.08
    >>
    -0.08
    〜
    -0.07
     balade
    -0.07
     -----
    -0.07
    >>,
    -0.07
    ియర్
    -0.07
    ;;
    -0.07
    ecera
    -0.07
    POSITIVE LOGITS
     allowable
    0.08
    удің
    0.08
     permissible
    0.08
     предусмотр
    0.08
     susc
    0.08
     petitions
    0.08
    Ave
    0.07
    ingss
    0.07
     придум
    0.07
     costit
    0.07
    Activations Density 0.001%

    No Known Activations