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. 15-RESID-POST-AA
    6. 19016
    Prev
    Next
    INDEX
    Explanations

    Minimizing distances to vertices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envel
    -0.09
     reche
    -0.09
     resten
    -0.08
    	callback
    -0.08
     callback
    -0.08
    hete
    -0.08
     ഇ
    -0.08
     typedef
    -0.08
     sts
    -0.08
     widening
    -0.08
    POSITIVE LOGITS
     Jury
    0.08
    oglob
    0.08
    점을
    0.08
     jury
    0.08
     foyer
    0.07
     भवन
    0.07
     centroid
    0.07
     nokt
    0.07
     communal
    0.07
     Central
    0.07
    Activations Density 0.013%

    No Known Activations