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. 11-RESID-POST-AA
    6. 88040
    Prev
    Next
    INDEX
    Explanations

    Chemical compounds

    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
     workbook
    -0.08
     Jacob
    -0.08
     bitmap
    -0.08
    Jacob
    -0.07
    rewrite
    -0.07
    	flags
    -0.07
    Hints
    -0.07
    Flags
    -0.07
    Tests
    -0.07
     flags
    -0.07
    POSITIVE LOGITS
    \Http
    0.09
     cous
    0.09
    phen
    0.09
     xi
    0.08
    xi
    0.08
    ‑
    0.08
    ξ
    0.08
     hydrocar
    0.08
     glycol
    0.08
     kest
    0.08
    Activations Density 0.010%

    No Known Activations