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. 130749
    Prev
    Next
    INDEX
    Explanations

    Disney theme parks

    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
    _DECREF
    -0.09
     вертик
    -0.08
     интер
    -0.08
     саб
    -0.08
    Unary
    -0.08
     নেত
    -0.08
     র
    -0.08
     реаг
    -0.08
     зл
    -0.08
     Unary
    -0.08
    POSITIVE LOGITS
    $I
    0.08
    Anal
    0.08
     Buffalo
    0.08
    .Art
    0.07
     bezoek
    0.07
     crítica
    0.07
     Anal
    0.07
     Animal
    0.07
    Washington
    0.07
    āina
    0.07
    Activations Density 0.002%

    No Known Activations