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. 117610
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ="$(
    -0.08
    Target
    -0.07
     Connie
    -0.07
     protr
    -0.07
    Lect
    -0.07
     explanatory
    -0.07
    Leaf
    -0.07
    LEV
    -0.07
    _TARGET
    -0.07
    _instr
    -0.07
    POSITIVE LOGITS
    reffen
    0.09
    .False
    0.08
     સેવ
    0.08
     rumored
    0.08
     совмест
    0.08
     arrière
    0.08
     Treffen
    0.08
    美容
    0.08
     Hvis
    0.07
     destinadas
    0.07
    Activations Density 0.010%

    No Known Activations