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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49286
    Prev
    Next
    INDEX
    Explanations

    peptides and proteins

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मन
    -0.09
     empen
    -0.09
     civilian
    -0.09
     annoyance
    -0.08
     ಮನ
    -0.08
     insist
    -0.08
     incó
    -0.08
     mana
    -0.08
     مبلغ
    -0.08
    noun
    -0.08
    POSITIVE LOGITS
     peptide
    0.15
     peptides
    0.15
     phosphorylation
    0.14
     Protein
    0.13
     ligand
    0.13
    RNA
    0.13
     SARS
    0.13
     molé
    0.13
     proteins
    0.13
     protéines
    0.13
    Activations Density 0.028%

    No Known Activations