© 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. 5335
    Prev
    Next
    INDEX
    Explanations

    German technical instructions

    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
    éiert
    -0.09
     appla
    -0.09
     rozp
    -0.09
    éieren
    -0.09
     Unterstüt
    -0.08
     controleren
    -0.08
    ituen
    -0.08
     zote
    -0.08
     plaatsen
    -0.08
     podp
    -0.08
    POSITIVE LOGITS
    beitung
    0.21
    ütung
    0.19
    ärkung
    0.19
    hnung
    0.18
    achtung
    0.18
    ertung
    0.17
    inderung
    0.17
    assung
    0.17
    ichtigung
    0.17
    tragung
    0.17
    Activations Density 0.010%

    No Known Activations