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. 98548
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    اصة
    -0.09
    都有
    -0.08
    gesture
    -0.08
     Animal
    -0.08
    اديمية
    -0.07
     AU
    -0.07
     Gesture
    -0.07
     gesture
    -0.07
    .Apply
    -0.07
     miejscu
    -0.07
    POSITIVE LOGITS
     öpp
    0.09
    чные
    0.08
     kansen
    0.08
    La
    0.08
     nai
    0.08
     Lá
    0.07
    ча
    0.07
     primary
    0.07
    فن
    0.07
    чный
    0.07
    Activations Density 0.000%

    No Known Activations