Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58582
    Prev
    Next
    INDEX
    Explanations

    â

    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
     pse
    -0.08
     Bol
    -0.08
     lod
    -0.08
     viable
    -0.08
     Kre
    -0.08
    /MS
    -0.07
     проз
    -0.07
     CSI
    -0.07
     doable
    -0.07
     pups
    -0.07
    POSITIVE LOGITS
    €“
    0.10
    -sama
    0.07
    €¦↵↵
    0.07
    €¦
    0.07
     Ro
    0.07
    €”
    0.07
    €œ
    0.07
     hum
    0.07
     restful
    0.07
    ў
    0.07
    Activations Density 0.015%

    No Known Activations