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. 130853
    Prev
    Next
    INDEX
    Explanations

    letter

    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
    €¢
    -0.09
     escl
    -0.08
    -going
    -0.08
     indeb
    -0.08
    ệp
    -0.08
    anzas
    -0.08
    ountries
    -0.08
    ENTS
    -0.08
    udades
    -0.08
    _THE
    -0.08
    POSITIVE LOGITS
    head
    0.10
    press
    0.10
    forms
    0.09
    formen
    0.09
    form
    0.09
    man
    0.09
    höhe
    0.09
    ken
    0.09
    size
    0.09
     sizing
    0.09
    Activations Density 0.002%

    No Known Activations