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. 29860
    Prev
    Next
    INDEX
    Explanations

    favorite

    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
     verh
    -0.09
     Permanent
    -0.08
     пространства
    -0.08
    Permanent
    -0.08
     demi
    -0.08
    ahs
    -0.08
     furnished
    -0.08
    يح
    -0.07
    alem
    -0.07
     Cin
    -0.07
    POSITIVE LOGITS
    avorite
    0.09
     hashtags
    0.08
     만큼
    0.08
    favorite
    0.08
     Obl
    0.08
     favorite
    0.08
     favoritas
    0.07
     trae
    0.07
     ప్రముఖ
    0.07
    estors
    0.07
    Activations Density 0.026%

    No Known Activations