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. 11767
    Prev
    Next
    INDEX
    Explanations

    Server

    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
     reliably
    -0.09
     basis
    -0.08
     лов
    -0.08
     Trap
    -0.08
     hole
    -0.08
    ար
    -0.08
     prosecution
    -0.08
     affid
    -0.07
    asile
    -0.07
     fiable
    -0.07
    POSITIVE LOGITS
     कोरोना
    0.08
    quelize
    0.08
    巨大
    0.08
     méc
    0.08
    CSR
    0.08
    एस
    0.07
     पार
    0.07
     did
    0.07
    _OP
    0.07
    主
    0.07
    Activations Density 0.001%

    No Known Activations