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. 15-RESID-POST-AA
    6. 19156
    Prev
    Next
    INDEX
    Explanations

    each

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     کرده
    -0.09
    iendo
    -0.08
    -members
    -0.08
     Members
    -0.08
    .Constants
    -0.07
    Jer
    -0.07
     fibres
    -0.07
     daarin
    -0.07
     rays
    -0.07
     members
    -0.07
    POSITIVE LOGITS
     сайын
    0.10
     kurzen
    0.10
     промеж
    0.09
     clearfix
    0.09
     intermediate
    0.08
     except
    0.08
     ഇട
    0.08
     interim
    0.08
     تحديث
    0.08
     шинэ
    0.08
    Activations Density 0.010%

    No Known Activations