© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54856
    Prev
    Next
    INDEX
    Explanations

    vector

    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
     Wikipédia
    -0.08
    ievable
    -0.08
     forcément
    -0.08
    issie
    -0.07
    -0.07
    _dim
    -0.07
     attributable
    -0.07
     sourced
    -0.07
    ieved
    -0.07
    円
    -0.07
    POSITIVE LOGITS
    -shot
    0.07
    -pe
    0.07
    -cl
    0.07
     इसमें
    0.07
    arner
    0.07
    -post
    0.07
    enom
    0.07
     Fro
    0.07
    -vars
    0.07
     पी
    0.07
    Activations Density 0.001%
    No Known Activations