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. 65305
    Prev
    Next
    INDEX
    Explanations

    Chemical molecules

    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
     subsid
    -0.08
     emoc
    -0.08
    -0.07
     physique
    -0.07
     情
    -0.07
     físico
    -0.07
     باد
    -0.07
     Adidas
    -0.07
     metast
    -0.07
     referral
    -0.07
    POSITIVE LOGITS
     кру
    0.09
    Liz
    0.08
     Hubbard
    0.08
    uins
    0.08
     mof
    0.08
    hou
    0.08
    kep
    0.08
    pla
    0.07
     belly
    0.07
     patt
    0.07
    Activations Density 0.002%

    No Known Activations