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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98044
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -gr
    -0.09
     Utf
    -0.09
    brates
    -0.08
    jong
    -0.08
    illong
    -0.08
     Maranh
    -0.08
    .bind
    -0.08
    ��
    -0.08
    Ij
    -0.08
    ettiin
    -0.08
    POSITIVE LOGITS
    Soft
    0.09
    Stable
    0.08
     stable
    0.08
     Soft
    0.08
     documentos
    0.08
    Pet
    0.08
    Elegant
    0.08
     garage
    0.08
    garage
    0.08
    Clean
    0.08
    Activations Density 0.001%

    No Known Activations