© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64660
    Prev
    Next
    INDEX
    Explanations

    G-spot stimulation

    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
     caric
    -0.09
    Policies
    -0.08
    Policy
    -0.08
     riesgos
    -0.08
     chinos
    -0.08
    லாம்
    -0.08
     Policies
    -0.08
    Conflict
    -0.08
     casser
    -0.08
    .publish
    -0.08
    POSITIVE LOGITS
     orgas
    0.10
     orgasm
    0.09
     loved
    0.09
     pleasurable
    0.09
     удоволь
    0.09
     stimulation
    0.09
    疼
    0.08
     आनंद
    0.08
    刺激
    0.08
     tactile
    0.08
    Activations Density 0.015%

    No Known Activations