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. 55897
    Prev
    Next
    INDEX
    Explanations

    parenthesis and brackets

    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
    (Not
    -0.07
    课程
    -0.07
    _cor
    -0.07
     பண
    -0.07
    ии
    -0.07
    ={↵
    -0.07
     Ne
    -0.06
    _roll
    -0.06
    rome
    -0.06
    POSITIVE LOGITS
     XOR
    0.09
     +
    0.08
     xor
    0.08
     плюс
    0.08
    所以
    0.08
     زائد
    0.08
     competed
    0.08
     iva
    0.08
     handwritten
    0.08
    ”和
    0.08
    Activations Density 0.100%

    No Known Activations