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. 97045
    Prev
    Next
    INDEX
    Explanations

    foot

    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
     voeten
    -0.09
     meters
    -0.09
     Fuß
    -0.09
    ownie
    -0.09
    anuts
    -0.08
     Feet
    -0.08
     NIV
    -0.08
    irtschaft
    -0.08
    Feet
    -0.08
     ফুট
    -0.08
    POSITIVE LOGITS
    sie
    0.10
    falls
    0.10
    locker
    0.10
    race
    0.10
    fall
    0.09
    ed
    0.09
    lo
    0.09
     festival
    0.09
    man
    0.08
    st
    0.08
    Activations Density 0.003%

    No Known Activations