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. 130949
    Prev
    Next
    INDEX
    Explanations

    text

    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
    Album
    -0.09
    Allowance
    -0.09
     Resolver
    -0.08
    Resolver
    -0.08
     &$
    -0.08
     $
    -0.08
     `$
    -0.08
     Alþ
    -0.08
    Remain
    -0.07
     Album
    -0.07
    POSITIVE LOGITS
    *
    0.12
    {
    0.11
    k
    0.10
    bf
    0.10
    back
    0.09
     tegel
    0.09
    %
    0.09
    {k
    0.09
     tarjoukset
    0.08
    `
    0.08
    Activations Density 0.011%

    No Known Activations