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. 98365
    Prev
    Next
    INDEX
    Explanations

    Words with "w"

    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
    ir
    -0.09
    -hit
    -0.09
    IR
    -0.08
    on
    -0.08
    99
    -0.08
    ira
    -0.08
    -0.07
     digne
    -0.07
    -winning
    -0.07
    APA
    -0.07
    POSITIVE LOGITS
    heel
    0.14
    heels
    0.14
    hee
    0.13
    HEEL
    0.13
    HE
    0.12
     HE
    0.12
    HELL
    0.10
    hell
    0.10
    he
    0.10
    ્હ
    0.10
    Activations Density 0.001%

    No Known Activations