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. 67650
    Prev
    Next
    INDEX
    Explanations

    journ

    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
     Eric
    -0.08
    -0.08
    nton
    -0.08
     Carpet
    -0.08
    bricas
    -0.07
     cylinder
    -0.07
    land
    -0.07
    -ranked
    -0.07
     governs
    -0.07
     carpet
    -0.07
    POSITIVE LOGITS
    /news
    0.08
     diariamente
    0.08
    olique
    0.08
     โ
    0.08
     కార్యక్రమ
    0.07
     antioxidant
    0.07
     लेख
    0.07
    ॉ
    0.07
     forgiveness
    0.07
     Ам
    0.07
    Activations Density 0.004%

    No Known Activations