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. 90165
    Prev
    Next
    INDEX
    Explanations

    width or PWM

    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
    Override
    -0.08
     tampil
    -0.07
     사진
    -0.07
    iris
    -0.07
     override
    -0.07
     collects
    -0.07
    ーム
    -0.07
     ijs
    -0.07
    .Override
    -0.07
    니
    -0.07
    POSITIVE LOGITS
    _length
    0.09
    _frequency
    0.09
     количества
    0.09
     امریک
    0.09
    Length
    0.09
     frequency
    0.09
     Länge
    0.09
     امریکہ
    0.09
    Boolean
    0.09
    Duration
    0.08
    Activations Density 0.004%

    No Known Activations