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. 97068
    Prev
    Next
    INDEX
    Explanations

    gr

    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
    changer
    -0.08
    -ay
    -0.08
    ೌ
    -0.08
    utom
    -0.08
    pes
    -0.08
     cohesive
    -0.08
    .navigate
    -0.07
    navigate
    -0.07
    ய்
    -0.07
    яли
    -0.07
    POSITIVE LOGITS
    abs
    0.10
    abbing
    0.09
    AB
    0.08
    ab
    0.08
     abs
    0.08
    ABS
    0.08
    illing
    0.08
     abortion
    0.08
     quotas
    0.07
    굴
    0.07
    Activations Density 0.001%

    No Known Activations