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. 98262
    Prev
    Next
    INDEX
    Explanations

    say "ios"

    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
    That
    -0.07
     =
    -0.07
     ->
    -0.07
    ss
    -0.07
     }
    -0.07
    ು
    -0.07
    ness
    -0.07
     dass
    -0.07
     *
    -0.07
     views
    -0.07
    POSITIVE LOGITS
     ios
    0.20
    ios
    0.16
     IOS
    0.12
    Ios
    0.12
    IOS
    0.11
    _ios
    0.11
    -ios
    0.10
    _FAST
    0.09
    /io
    0.09
     иностранных
    0.09
    Activations Density 0.002%

    No Known Activations