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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5769
    Prev
    Next
    INDEX
    Explanations

    630

    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
    ూత
    -0.08
     аст
    -0.07
     beaux
    -0.07
    ighting
    -0.07
     pocas
    -0.07
     fright
    -0.07
    Beam
    -0.07
     As
    -0.07
    Heal
    -0.07
    ICKS
    -0.07
    POSITIVE LOGITS
    edes
    0.11
    inerja
    0.11
    eluaran
    0.10
    edere
    0.10
    Tu
    0.10
     Tu
    0.09
    edal
    0.09
    ualitas
    0.09
    egiatan
    0.09
    ágrafo
    0.08
    Activations Density 0.001%

    No Known Activations