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. 11774
    Prev
    Next
    INDEX
    Explanations

    terms like

    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
    /platform
    -0.09
     @_;↵↵
    -0.08
     lavish
    -0.08
    /Icon
    -0.08
     @_;↵
    -0.07
    	var
    -0.07
    ед
    -0.07
    欣
    -0.07
     produks
    -0.07
     खू
    -0.07
    POSITIVE LOGITS
     പോയ
    0.08
     utile
    0.08
    ppel
    0.08
    _lb
    0.08
    LB
    0.07
    .interpolate
    0.07
    ctp
    0.07
     �
    0.07
     unus
    0.07
    .pp
    0.07
    Activations Density 0.004%

    No Known Activations