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. 113893
    Prev
    Next
    INDEX
    Explanations

    a

    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
     Ders
    -0.08
     нават
    -0.08
     nettet
    -0.08
    યો
    -0.08
     Belly
    -0.08
    制
    -0.08
     Tallinn
    -0.08
     Abril
    -0.08
     vertel
    -0.08
    اطع
    -0.08
    POSITIVE LOGITS
    sex
    0.08
    Group
    0.08
     mission
    0.07
     priori
    0.07
     собой
    0.07
    EXP
    0.07
    Ds
    0.07
    ाधिक
    0.07
    dv
    0.07
    qs
    0.07
    Activations Density 0.109%

    No Known Activations