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. 65464
    Prev
    Next
    INDEX
    Explanations

    ons

    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
    Mob
    -0.09
    Fb
    -0.08
    four
    -0.07
    jos
    -0.07
    Gr
    -0.07
     mangan
    -0.07
     Gao
    -0.07
    fore
    -0.07
    mob
    -0.07
     mob
    -0.07
    POSITIVE LOGITS
    ेदारी
    0.09
     havoc
    0.08
     нравится
    0.08
     вин
    0.08
    作用
    0.08
     გამო�
    0.08
     исключ
    0.08
     interessiert
    0.08
     interés
    0.08
    ამ
    0.08
    Activations Density 0.186%

    No Known Activations