Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56071
    Prev
    Next
    INDEX
    Explanations

    Spanish language

    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
     tri
    -0.10
    िश
    -0.08
    فا
    -0.07
    {}",
    -0.07
    없이
    -0.07
    imh
    -0.07
    -0.07
    Tri
    -0.07
    dia
    -0.07
    راً
    -0.07
    POSITIVE LOGITS
    anya
    0.08
    .reward
    0.08
     counseling
    0.08
     здрав
    0.07
    _reward
    0.07
     DPS
    0.07
     Reward
    0.07
     консульт
    0.07
    -town
    0.07
     iniz
    0.07
    Activations Density 0.000%

    No Known Activations