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. 77540
    Prev
    Next
    INDEX
    Explanations

    Baking

    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
     pokemon
    -0.09
    pokemon
    -0.09
    ığını
    -0.08
     recic
    -0.08
    Masc
    -0.08
     miesię
    -0.08
     Inicio
    -0.08
     Masc
    -0.07
     Mask
    -0.07
    мын
    -0.07
    POSITIVE LOGITS
     burnt
    0.09
     сеть
    0.09
     crisp
    0.08
    薄
    0.08
     crispy
    0.08
     réseau
    0.08
     thin
    0.08
     offr
    0.08
     brzo
    0.08
     cracked
    0.08
    Activations Density 0.018%

    No Known Activations