Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42271
    Prev
    Next
    INDEX
    Explanations

    exposure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fé
    -0.07
    -0.07
    וכל
    -0.07
    Repositorio
    -0.07
    .Dimension
    -0.07
    -av
    -0.07
     Odds
    -0.07
    Afin
    -0.07
     Jordi
    -0.07
     kruis
    -0.07
    POSITIVE LOGITS
     shots
    0.09
    /night
    0.08
     ноч
    0.08
    摄影
    0.08
     thu
    0.08
     midnight
    0.08
     रात
    0.07
     shimmering
    0.07
     artistry
    0.07
     fotograf
    0.07
    Activations Density 0.001%

    No Known Activations