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. 98547
    Prev
    Next
    INDEX
    Explanations

    A

    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
    атә
    -0.13
     ের
    -0.13
    ալ
    -0.12
    ուռ
    -0.12
    ייַט
    -0.12
    дошт
    -0.12
    итиниң
    -0.12
     אבער
    -0.12
     Erotiske
    -0.12
    արաբաղ
    -0.12
    POSITIVE LOGITS
    cknow
    0.17
    ucune
    0.16
    loha
    0.16
    xiom
    0.16
    cknowled
    0.15
    UDIO
    0.15
    ABB
    0.15
    CTIONS
    0.14
    yesha
    0.14
    ffects
    0.13
    Activations Density 0.133%

    No Known Activations