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. 7-RESID-POST-AA
    6. 131031
    Prev
    Next
    INDEX
    Explanations

    Computer science algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AUX
    -0.08
    کرا
    -0.08
    #do
    -0.07
    ț
    -0.07
     ascii
    -0.07
    sett
    -0.07
     الطبية
    -0.07
    @app
    -0.07
    aspect
    -0.07
     Sehens
    -0.07
    POSITIVE LOGITS
    _Remove
    0.07
    _diag
    0.07
    0.07
     изб
    0.07
     eri
    0.07
    662
    0.07
    _Order
    0.07
    alid
    0.07
    _bid
    0.07
    Cheque
    0.07
    Activations Density 0.000%

    No Known Activations