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. 76002
    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
     չենք
    -0.09
     Lots
    -0.08
     gleichen
    -0.08
    Lots
    -0.08
     [&
    -0.08
     większo
    -0.08
     với
    -0.08
     և
    -0.08
    —including
    -0.08
     չէր
    -0.08
    POSITIVE LOGITS
     upcoming
    0.08
     Bestandteil
    0.08
     created
    0.07
     hypothetical
    0.07
    高级
    0.07
     cobertura
    0.07
     apex
    0.07
     modeling
    0.07
    203
    0.07
     movement
    0.07
    Activations Density 0.036%

    No Known Activations