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. 2346
    Prev
    Next
    INDEX
    Explanations

    blessed

    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
     agit
    -0.08
    -0.07
     Hele
    -0.07
     стор
    -0.07
     moto
    -0.07
     अत
    -0.07
     CNS
    -0.07
    �
    -0.07
     vert
    -0.07
    Fra
    -0.07
    POSITIVE LOGITS
     regard
    0.09
     аң
    0.07
     Чем
    0.07
    .Gr
    0.07
    gant
    0.07
     Harden
    0.07
    kom
    0.07
    ↓
    0.07
    mods
    0.07
     ava
    0.07
    Activations Density 0.004%

    No Known Activations