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. 112298
    Prev
    Next
    INDEX
    Explanations

    folded or crossed arms

    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
    _pow
    -0.09
     Walsh
    -0.08
     Cp
    -0.08
    Mk
    -0.08
     collectible
    -0.08
     dbg
    -0.08
     grub
    -0.07
     tiny
    -0.07
    README
    -0.07
     Bedien
    -0.07
    POSITIVE LOGITS
    圈
    0.09
    بان
    0.08
     orn
    0.08
     pessoais
    0.08
    parm
    0.07
    ceeds
    0.07
     ruime
    0.07
     sarili
    0.07
    ='"
    0.07
    おります
    0.07
    Activations Density 0.003%

    No Known Activations