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. 97959
    Prev
    Next
    INDEX
    Explanations

    Proportions

    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
     bordo
    -0.08
     wyją
    -0.08
     exceptions
    -0.08
    Exception
    -0.08
    {return
    -0.08
     Exceptions
    -0.08
     этаж
    -0.07
     uitzonder
    -0.07
     وهل
    -0.07
    blas
    -0.07
    POSITIVE LOGITS
     proportional
    0.21
     proportion
    0.20
     proporcional
    0.19
     proportions
    0.19
    比例
    0.17
     units
    0.17
    units
    0.16
    _units
    0.16
    _unit
    0.15
     unit
    0.15
    Activations Density 0.163%

    No Known Activations