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. 12026
    Prev
    Next
    INDEX
    Explanations

    fiber

    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
     tentative
    -0.08
    _running
    -0.08
    _needed
    -0.07
     rugged
    -0.07
     commanders
    -0.07
     needed
    -0.07
     perched
    -0.07
    _pending
    -0.07
    Running
    -0.07
     tac
    -0.07
    POSITIVE LOGITS
     kombiniert
    0.09
     amalg
    0.09
     recycled
    0.09
     bloco
    0.09
     компакт
    0.08
     combinação
    0.08
     SUPER
    0.08
     composites
    0.08
     fiberglass
    0.08
     blends
    0.08
    Activations Density 0.014%

    No Known Activations