© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129292
    Prev
    Next
    INDEX
    Explanations

    microbiome analysis

    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
     cigarettes
    -0.09
    Helping
    -0.08
    Receiving
    -0.08
    idd
    -0.07
     volontaire
    -0.07
     factoring
    -0.07
     tug
    -0.07
     nesta
    -0.07
     bege
    -0.07
     eyesight
    -0.07
    POSITIVE LOGITS
     biodivers
    0.11
     taxonomy
    0.11
     distro
    0.10
    Alien
    0.10
     archae
    0.10
     Archae
    0.10
     biodiversity
    0.10
     microbial
    0.09
     taxa
    0.09
     algae
    0.09
    Activations Density 0.006%

    No Known Activations