Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98566
    Prev
    Next
    INDEX
    Explanations

    the

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasting
    -0.10
    acting
    -0.09
    er's
    -0.09
    anggung
    -0.09
    itser
    -0.09
    -performing
    -0.09
    unahing
    -0.09
    it's
    -0.09
    eroen
    -0.09
     documenting
    -0.09
    POSITIVE LOGITS
     circumference
    0.10
    _LINE
    0.09
    _segments
    0.09
     vicinity
    0.09
     segment
    0.09
     midpoint
    0.09
     given
    0.09
     line
    0.09
    _SEG
    0.08
     positively
    0.08
    Activations Density 0.098%

    No Known Activations