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. 97055
    Prev
    Next
    INDEX
    Explanations

    parap

    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
    amanya
    -0.10
    ப்பட
    -0.09
    имер
    -0.08
     Lour
    -0.08
    _IMPORT
    -0.08
     Haram
    -0.08
     afore
    -0.08
     Advert
    -0.08
    им
    -0.08
     bloss
    -0.08
    POSITIVE LOGITS
    pro
    0.08
     twee
    0.08
    uka
    0.08
    .Height
    0.07
    (
    0.07
    -two
    0.07
    (pro
    0.07
    -high
    0.07
     TWO
    0.07
     navigation
    0.07
    Activations Density 0.000%

    No Known Activations