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. 58555
    Prev
    Next
    INDEX
    Explanations

    bouncing ball height calculation

    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
    णी
    -0.07
     normative
    -0.07
     บ
    -0.07
     sext
    -0.07
    normalize
    -0.07
     לת
    -0.07
     בש
    -0.07
     hack
    -0.07
     expense
    -0.07
     בת
    -0.07
    POSITIVE LOGITS
    _decay
    0.09
     despair
    0.09
    Decay
    0.09
     transmission
    0.09
    减少
    0.08
    anach
    0.08
     తగ్గ
    0.08
    続
    0.08
     glycer
    0.08
    _archive
    0.08
    Activations Density 0.029%

    No Known Activations