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. 23235
    Prev
    Next
    INDEX
    Explanations

    Why

    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
    ğim
    -0.08
     Denis
    -0.08
     Apparently
    -0.08
     Eas
    -0.08
    SOS
    -0.08
    fas
    -0.08
     Tempo
    -0.07
    -0.07
     dru
    -0.07
     Dro
    -0.07
    POSITIVE LOGITS
     spelled
    0.08
    IG
    0.08
    ంటి
    0.08
     данном
    0.08
    AV
    0.07
     वि�
    0.07
     abr
    0.07
    итель
    0.07
    ons
    0.07
    ింత
    0.07
    Activations Density 0.024%

    No Known Activations