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. 88012
    Prev
    Next
    INDEX
    Explanations

    Dynamics 365

    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
    hada
    -0.08
     macho
    -0.08
    라이
    -0.08
    女性
    -0.08
     Freundin
    -0.08
     reunion
    -0.07
    حنة
    -0.07
     Signature
    -0.07
    typedef
    -0.07
    signature
    -0.07
    POSITIVE LOGITS
     custod
    0.08
     vex
    0.08
     remit
    0.07
     cust
    0.07
    Cust
    0.07
     games
    0.07
     tasked
    0.07
     remodeling
    0.07
     roaming
    0.07
     рем
    0.07
    Activations Density 0.002%

    No Known Activations