© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102814
    Prev
    Next
    INDEX
    Explanations

    Chemical concentrations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysize
    -0.09
    Hardware
    -0.08
     hardware
    -0.08
     indicadores
    -0.08
    Performance
    -0.08
     electricity
    -0.08
     Playstation
    -0.08
     asphalt
    -0.08
    duino
    -0.08
     solder
    -0.08
    POSITIVE LOGITS
     mmol
    0.17
     concentrations
    0.16
     concentration
    0.14
     mg
    0.13
     концентра
    0.13
    浓
    0.12
     농
    0.12
     mol
    0.12
     concentração
    0.11
     Konzentr
    0.11
    Activations Density 0.007%

    No Known Activations