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. 23-RESID-POST-AA
    6. 98269
    Prev
    Next
    INDEX
    Explanations

    gentle slopes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mountain
    -0.09
     mountainous
    -0.09
     पर्व
    -0.09
     alpine
    -0.09
     Maze
    -0.09
     깊
    -0.09
     Mountains
    -0.09
     tief
    -0.09
     profonde
    -0.09
     Crossing
    -0.09
    POSITIVE LOGITS
     gentle
    0.11
     declines
    0.09
     decline
    0.09
     slight
    0.09
    gent
    0.09
     und
    0.08
     declined
    0.08
     sides
    0.08
    sl
    0.08
     grades
    0.08
    Activations Density 0.008%

    No Known Activations