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. 7-RESID-POST-AA
    6. 131008
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /root
    -0.09
     초
    -0.08
     psi
    -0.08
     보면
    -0.08
     crest
    -0.08
     guste
    -0.08
    teresse
    -0.08
    ուխ
    -0.08
     돌
    -0.08
     حك
    -0.08
    POSITIVE LOGITS
     nale
    0.08
    app
    0.07
     fetching
    0.07
     Eddy
    0.07
    研
    0.07
     GOP
    0.07
    <N
    0.07
    BG
    0.07
    unexpected
    0.07
     narciss
    0.07
    Activations Density 0.007%

    No Known Activations