Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 112987
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Masa
    -0.07
     piste
    -0.07
     wirklich
    -0.07
    Deadline
    -0.07
     зам
    -0.06
     masa
    -0.06
     Seele
    -0.06
    Original
    -0.06
     columns
    -0.06
     );↵
    -0.06
    POSITIVE LOGITS
     jeweils
    0.10
     соответственно
    0.09
     respective
    0.09
     jeweiligen
    0.09
     opposing
    0.08
    ijão
    0.08
     respectively
    0.08
     stř
    0.08
     jewe
    0.08
    baix
    0.08
    Activations Density 0.526%

    No Known Activations