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. 112051
    Prev
    Next
    INDEX
    Explanations

    Solubility in organic solvents

    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
    hammer
    -0.09
     lider
    -0.08
     lighthouse
    -0.08
     engraved
    -0.08
     Lighthouse
    -0.07
    Unlock
    -0.07
    Hammer
    -0.07
     blueprint
    -0.07
    苗
    -0.07
     vandal
    -0.07
    POSITIVE LOGITS
     solvents
    0.19
     solvent
    0.16
     দ্র
    0.12
     liquids
    0.10
     mixtures
    0.10
     раствор
    0.10
     viscos
    0.10
     liqu
    0.10
     chl
    0.10
     soluble
    0.10
    Activations Density 0.010%

    No Known Activations