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. 60642
    Prev
    Next
    INDEX
    Explanations

    Chemistry solutions and concentrations

    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
     pelvis
    -0.09
    Awards
    -0.08
     amput
    -0.08
    Algorithms
    -0.08
     wings
    -0.08
    魂
    -0.08
     leash
    -0.07
    翼
    -0.07
     prophet
    -0.07
     पुरस्कार
    -0.07
    POSITIVE LOGITS
     concentrations
    0.15
    浓
    0.15
     концентра
    0.15
     concentration
    0.14
     concentración
    0.13
     koncentr
    0.13
     Konzentr
    0.13
     concentração
    0.12
     dosage
    0.11
     dosing
    0.11
    Activations Density 0.009%

    No Known Activations