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. 98310
    Prev
    Next
    INDEX
    Explanations

    GDP and calculations

    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
     تس
    -0.08
    ẹgẹbi
    -0.08
     bí
    -0.08
    ћи
    -0.08
    gelopen
    -0.07
    férence
    -0.07
     ار
    -0.07
    μών
    -0.07
    ëtt
    -0.07
    xffffffff
    -0.07
    POSITIVE LOGITS
    ujarati
    0.18
    a
    0.16
    it
    0.13
    RU
    0.13
    PU
    0.13
    R
    0.13
    ehova
    0.13
    LOBAL
    0.12
    al
    0.12
    O
    0.12
    Activations Density 0.004%

    No Known Activations