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. 60954
    Prev
    Next
    INDEX
    Explanations

    SCP

    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
     stereo
    -0.08
    ぱ
    -0.08
    clr
    -0.08
     bubb
    -0.08
    agrad
    -0.07
    _PACK
    -0.07
     detached
    -0.07
    岭
    -0.07
    Packed
    -0.07
    packed
    -0.07
    POSITIVE LOGITS
     editorial
    0.10
     Universe
    0.10
     universe
    0.09
     Encyclopedia
    0.09
    iverse
    0.08
     catalogue
    0.08
     fictional
    0.08
     encyclopedia
    0.08
     Articles
    0.08
     портал
    0.08
    Activations Density 0.002%

    No Known Activations