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. 44117
    Prev
    Next
    INDEX
    Explanations

    it

    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
    _BIN
    -0.09
     теперь
    -0.07
    .row
    -0.07
    昨
    -0.07
     Pine
    -0.07
    Fil
    -0.07
     ahora
    -0.07
     Fil
    -0.07
     Barber
    -0.07
    !\
    -0.07
    POSITIVE LOGITS
    usually
    0.14
    Often
    0.14
     Often
    0.13
     अक्सर
    0.13
     biasanya
    0.13
    often
    0.13
     зачастую
    0.13
    通常
    0.13
     usually
    0.12
     souvent
    0.12
    Activations Density 0.524%

    No Known Activations