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. 98283
    Prev
    Next
    INDEX
    Explanations

    �

    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
    EL
    -0.08
    of
    -0.08
    ISE
    -0.07
    িলে
    -0.07
    Trade
    -0.07
    ಿತ್ರ
    -0.07
    ेष
    -0.07
    offs
    -0.07
    olecule
    -0.07
     Trade
    -0.07
    POSITIVE LOGITS
     waypoint
    0.10
     Primavera
    0.09
    endente
    0.08
    ваў
    0.08
     sposób
    0.08
     damer
    0.08
    ânico
    0.08
     llega
    0.07
     manera
    0.07
     måde
    0.07
    Activations Density 0.000%

    No Known Activations