Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2287
    Prev
    Next
    INDEX
    Explanations

    comfortable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trit
    -0.08
     amplified
    -0.08
    -PCR
    -0.07
     Amph
    -0.07
     Ted
    -0.07
     Glam
    -0.07
     bibli
    -0.07
    akin
    -0.07
    čan
    -0.07
     kullanıcı
    -0.07
    POSITIVE LOGITS
     cruising
    0.09
     ache
    0.08
     Hom
    0.08
     accl
    0.08
    脱
    0.08
     moto
    0.08
     Mosaic
    0.07
    (acc
    0.07
    (KEY
    0.07
     rédu
    0.07
    Activations Density 0.005%

    No Known Activations