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. 119304
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Roche
    -0.09
    Η
    -0.08
    用了
    -0.08
    $q
    -0.07
    Arithmetic
    -0.07
     warming
    -0.07
    rama
    -0.07
    อยู่
    -0.07
    好了
    -0.07
     toestand
    -0.07
    POSITIVE LOGITS
     nargin
    0.11
     varargin
    0.10
     cs
    0.08
    (:,
    0.08
     ca
    0.08
     Paper
    0.08
     charset
    0.07
    _CERT
    0.07
     Patel
    0.07
     MATLAB
    0.07
    Activations Density 0.008%

    No Known Activations