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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78514
    Prev
    Next
    INDEX
    Explanations

    warnings

    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
     päev
    -0.08
    范
    -0.08
    جابة
    -0.07
     الخ
    -0.07
     എത്ത
    -0.07
     වෙ
    -0.07
     mö
    -0.07
     വ്യ
    -0.07
     جد
    -0.07
     biom
    -0.07
    POSITIVE LOGITS
     Civilization
    0.09
    >Please
    0.08
    castle
    0.08
     cauza
    0.08
     Cha
    0.08
    esai
    0.08
     Own
    0.08
     Wanted
    0.07
     Ursachen
    0.07
    oureux
    0.07
    Activations Density 0.000%

    No Known Activations