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. 111710
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    iriman
    -0.09
     procesu
    -0.08
    valid
    -0.08
    /filter
    -0.08
    הליך
    -0.08
    urlaub
    -0.08
    phony
    -0.08
    destroy
    -0.07
    justify
    -0.07
    anc
    -0.07
    POSITIVE LOGITS
     nan
    0.08
     oblige
    0.08
     atenção
    0.08
     assistance
    0.08
     എന്റെ
    0.08
     Attention
    0.08
     probeer
    0.07
     snacks
    0.07
     نش
    0.07
     Jing
    0.07
    Activations Density 0.005%

    No Known Activations